agentleFS
Sign inStart free
Ch1rpysCh1rpys/Mirrai/skill-engine/SKILL.md

dot-skill

Skill1.3k starsChanged 22 days agoMITView on GitHub

Mirrai 数字分身技能引擎——把聊天素材与公开研究蒸馏成可安装的人格技能包（同事 / 亲密关系 / 公众人物），并把技能包安装到 Claude Code、OpenClaw、Codex、Hermes。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 1

    1. Ch1rpy2613/Mirrai★ 1.3k100% same

    Edited · 0

    None found.

    Wrote their own version · 1

    1. SuperMate-Ai/SuperMate-Harness-System★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Create a free account to mount
Files
SKILL.md

Dot Skill Engine

skill-engine/ 是 Mirrai 的技能引擎本体：它是一套「元技能」，负责把素材蒸馏成一个人格技能包，并把技能包安装到各个 Agent 宿主。

组成

  • prompts/ —— 各角色族（同事 / 亲密关系 / 公众人物）的提示词。
  • prompts/registry.json —— 提示词的唯一事实来源：family（可选 profile）+ stage → 文件路径。
  • references/ —— 深度研究档位的方法论文档。
  • tools/ —— Python 工具链：素材采集、技能包写入、各宿主安装器、质量门。

蒸馏流程

  1. intake 收集素材（聊天记录、上传文件、公开资料）。
  2. analyzing_persona 抽取行为模式，building 写出结构化画像，merging 归一到统一契约。
  3. 公众人物的 budget-unfriendly 档位额外走研究四段：research → audit → synthesis → validation，并由 tools/research/quality_check.py 做代码级质量门。

技能包写入

tools/skill_writer.py 负责生成 SKILL.md、work.md、persona.md 与 manifest.json；--work / --persona 传入内容文件路径，--slug / --base-dir 决定输出位置。

安装到宿主

  • Claude Code —— tools/install_claude_generated_skill.py
  • OpenClaw —— tools/install_openclaw_generated_skill.py
  • Codex —— tools/install_codex_generated_skill.py
  • Hermes —— tools/install_hermes_skill.py

使用约束

  • 生成的技能正文不得包含代码块、> 引用块与 HH:MM:SS 时间戳，否则版权检查判定失败。
  • 研究笔记必须使用 merge_research.py 认识的小节标题，并按 Source weight: N、一手、Question: 的写法记录证据。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free